arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.15294cs.AI
收藏

EAA: 用视觉语言模型代理自动化材料表征

EAA: Automating materials characterization with vision language model agents

Argonne National Laboratory(阿贡国家实验室);Advanced Photon Source(先进光子源);Data Science and Learning Division(数据科学与学习 division);Department of Radiation Oncology(放射肿瘤学系);Northwestern University(西北大学)

Ming Du, Yanqi Luo, Srutarshi Banerjee, Michael Wojcik, Jelena Popovic, Mathew J. Cherukara

AI总结:

EAA利用视觉语言模型代理自动化材料表征,通过多模态推理和工具增强操作提升显微镜实验效率,减少操作负担并降低用户专业门槛。

摘要:

我们提出了实验自动化代理(EAA),一种由视觉语言模型驱动的代理系统,旨在自动化复杂的显微镜实验流程。EAA集成了多模态推理、工具增强操作和可选的长期记忆,以支持自主流程和交互式用户引导测量。该系统基于灵活的任务管理架构,能够实现从完全由代理驱动的自动化流程到逻辑定义的常规操作,后者嵌入了局部LLM查询。EAA还提供了一个现代的工具生态系统,具有与模型上下文协议(MCP)的双向兼容性,允许仪器控制工具在不同应用之间被消费或提供。我们在Advanced Photon Source的成像光束线上展示了EAA,包括自动区板聚焦、用自然语言描述的特征搜索和交互式数据采集。这些结果展示了视觉能力的代理如何提高光束线效率、减少操作负担并降低用户的专业门槛。

英文摘要:

We present Experiment Automation Agents (EAA), a vision-language-model-driven agentic system designed to automate complex experimental microscopy workflows. EAA integrates multimodal reasoning, tool-augmented action, and optional long-term memory to support both autonomous procedures and interactive user-guided measurements. Built on a flexible task-manager architecture, the system enables workflows ranging from fully agent-driven automation to logic-defined routines that embed localized LLM queries. EAA further provides a modern tool ecosystem with two-way compatibility for Model Context Protocol (MCP), allowing instrument-control tools to be consumed or served across applications. We demonstrate EAA at an imaging beamline at the Advanced Photon Source, including automated zone plate focusing, natural language-described feature search, and interactive data acquisition. These results illustrate how vision-capable agents can enhance beamline efficiency, reduce operational burden, and lower the expertise barrier for users.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑